Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3452 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.4901. Min Act: -0.0000

Data Index: 747120 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.4777. Min Act: -0.0000

Data Index: 1519067 (Python Code)

Max Activating Token Index: 422

Text #2

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.4030. Min Act: -0.0000

Data Index: 772760 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.3611. Min Act: -0.0000

Data Index: 167785 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.4894. Min Act: -0.0000

Data Index: 782354 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.3881. Min Act: -0.0000

Data Index: 1020328 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.3399. Min Act: -0.0000

Data Index: 79337 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.3579. Min Act: -0.0000

Data Index: 249060 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.3300. Min Act: -0.0000

Data Index: 559685 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.2164. Min Act: -0.0000

Data Index: 81863 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.0704. Min Act: -0.0000

Data Index: 1099587 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.1596. Min Act: -0.0000

Data Index: 1078596 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.3969. Min Act: -0.0000

Data Index: 419966 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.1583. Min Act: -0.0000

Data Index: 1028968 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.2316. Min Act: -0.0000

Data Index: 85891 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.2232. Min Act: -0.0000

Data Index: 500802 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.4726. Min Act: -0.0000

Data Index: 656821 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.2564. Min Act: -0.0000

Data Index: 357759 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.2523. Min Act: -0.0000

Data Index: 953988 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 2.4901. Min Range: -2.4901

Max Act: 2.1249. Min Act: -0.0000

Data Index: 827095 (C4 (Web Text))

Max Activating Token Index: 508